The graphic processing unit (GPU) makers like Nvidia and AMD have been courting supercomputer makers as the future of the massively parallel high-performance computer (HPC). Now, however, Intel has challenged that wisdom with a massively parallel x86 architecture called many-integrted core (MIC). Intel's presentation at Hot Chips last month details why they think MIC--and its first implementation, the 50+ core Xeon Phi--beats GPUs in accelerating the supercomputers of the future: R. Colin Johnson
Here is what Go-Parallel says about MIC versus GPU: Xeon Phi lead architect George Chrysos presented comparisons between using Xeon Phi co-processors instead of graphics-processor units (GPUs) at the recent Hot Chips conference. According to the Top500 Super Computer Sites ranking, Intel’s many-integrated core (MIC) architecture not only outperformed the two top GPU-based supercomputers on the most recent Top500 list, but was also “greener” by virtue of providing more performance-per-Watt.